note-optimizer
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided article content for optimization, which presents a surface for indirect prompt injection.\n
- Ingestion points: User-supplied article text as defined in FORMS.md.\n
- Boundary markers: Absent; the instructions do not implement specific delimiters to isolate user input from agent instructions.\n
- Capability inventory: The skill provides a Python script (scripts/export_to_markdown.py) that performs file read and write operations on the local file system.\n
- Sanitization: Absent; user-provided text is processed and exported without filtering or escaping.\n- [COMMAND_EXECUTION]: The skill includes a Python utility script (
scripts/export_to_markdown.py) for exporting optimized articles. This script uses standard libraries for file and path management and does not execute arbitrary or unauthorized commands.
Audit Metadata